Hugging Face's logo

stulcrad
/
CNEC_2_0_Supertypes_robeczech-base

Token Classification
Transformers
Safetensors
roberta
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
stulcrad commited on
Commit
72756bb
·
verified ·
1 Parent(s): d907f2a

Model save

Browse files
Files changed (2) hide show
  1. README.md +26 -19
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,16 +25,16 @@ model-index:
25
  metrics:
26
  - name: Precision
27
  type: precision
28
- value: 0.8504930966469428
29
  - name: Recall
30
  type: recall
31
- value: 0.8905410987195373
32
  - name: F1
33
  type: f1
34
- value: 0.8700564971751411
35
  - name: Accuracy
36
  type: accuracy
37
- value: 0.9632960247008877
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,11 +44,11 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.1638
48
- - Precision: 0.8505
49
- - Recall: 0.8905
50
- - F1: 0.8701
51
- - Accuracy: 0.9633
52
 
53
  ## Model description
54
 
@@ -68,22 +68,29 @@ More information needed
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
- - train_batch_size: 64
72
- - eval_batch_size: 64
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
- - num_epochs: 25
77
 
78
  ### Training results
79
 
80
- | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
- |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
- | 0.6262 | 4.42 | 500 | 0.2328 | 0.8091 | 0.8125 | 0.8108 | 0.9524 |
83
- | 0.1941 | 8.85 | 1000 | 0.1757 | 0.8235 | 0.8711 | 0.8466 | 0.9595 |
84
- | 0.1204 | 13.27 | 1500 | 0.1661 | 0.8422 | 0.8860 | 0.8635 | 0.9629 |
85
- | 0.0914 | 17.7 | 2000 | 0.1633 | 0.8410 | 0.8868 | 0.8633 | 0.9629 |
86
- | 0.0756 | 22.12 | 2500 | 0.1638 | 0.8505 | 0.8905 | 0.8701 | 0.9633 |
 
 
 
 
 
 
 
87
 
88
 
89
  ### Framework versions
 
25
  metrics:
26
  - name: Precision
27
  type: precision
28
+ value: 0.8465443186255369
29
  - name: Recall
30
  type: recall
31
+ value: 0.8954977282114829
32
  - name: F1
33
  type: f1
34
+ value: 0.8703331995182658
35
  - name: Accuracy
36
  type: accuracy
37
+ value: 0.9622153608645311
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
44
 
45
  This model is a fine-tuned version of [ufal/robeczech-base](https://huggingface.co/ufal/robeczech-base) on the cnec dataset.
46
  It achieves the following results on the evaluation set:
47
+ - Loss: 0.2372
48
+ - Precision: 0.8465
49
+ - Recall: 0.8955
50
+ - F1: 0.8703
51
+ - Accuracy: 0.9622
52
 
53
  ## Model description
54
 
 
68
 
69
  The following hyperparameters were used during training:
70
  - learning_rate: 2e-05
71
+ - train_batch_size: 32
72
+ - eval_batch_size: 32
73
  - seed: 42
74
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
75
  - lr_scheduler_type: linear
76
+ - num_epochs: 80
77
 
78
  ### Training results
79
 
80
+ | Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
81
+ |:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
82
+ | 0.3253 | 6.67 | 1500 | 0.1982 | 0.7887 | 0.8034 | 0.7960 | 0.9492 |
83
+ | 0.1548 | 13.33 | 3000 | 0.1627 | 0.8249 | 0.8699 | 0.8468 | 0.9600 |
84
+ | 0.1049 | 20.0 | 4500 | 0.1664 | 0.8245 | 0.8769 | 0.8499 | 0.9610 |
85
+ | 0.0767 | 26.67 | 6000 | 0.1777 | 0.84 | 0.8848 | 0.8618 | 0.9616 |
86
+ | 0.0628 | 33.33 | 7500 | 0.1800 | 0.8510 | 0.8868 | 0.8685 | 0.9622 |
87
+ | 0.0504 | 40.0 | 9000 | 0.1952 | 0.8471 | 0.8926 | 0.8693 | 0.9630 |
88
+ | 0.042 | 46.67 | 10500 | 0.2146 | 0.85 | 0.8918 | 0.8704 | 0.9628 |
89
+ | 0.0359 | 53.33 | 12000 | 0.2190 | 0.8473 | 0.8959 | 0.8709 | 0.9632 |
90
+ | 0.0315 | 60.0 | 13500 | 0.2196 | 0.8480 | 0.8943 | 0.8705 | 0.9631 |
91
+ | 0.0284 | 66.67 | 15000 | 0.2283 | 0.8459 | 0.8976 | 0.8709 | 0.9621 |
92
+ | 0.0272 | 73.33 | 16500 | 0.2368 | 0.8444 | 0.8947 | 0.8688 | 0.9620 |
93
+ | 0.0243 | 80.0 | 18000 | 0.2372 | 0.8465 | 0.8955 | 0.8703 | 0.9622 |
94
 
95
 
96
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26dbddcd3f9741eb684f9ad599a42ea3ae3dad207baa73c5b28d5115f097e862
3
  size 501617084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e3f6b5b9880027c3eee6bdd5be2af7b002c20b010aeace39fbb93779cd78f9
3
  size 501617084